© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 42161
    Prev
    Next
    INDEX
    Explanations

    navigation commands or prompts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    azz
    -0.07
    ption
    -0.07
     Paren
    -0.07
    spr
    -0.06
    place
    -0.06
     Bernstein
    -0.06
    oo
    -0.06
    752
    -0.06
    lectric
    -0.06
    ERSHEY
    -0.06
    POSITIVE LOGITS
    deme
    0.06
    ipi
    0.06
    lius
    0.06
    ίγ
    0.06
    malink
    0.06
    URRED
    0.06
    493
    0.06
    ancode
    0.06
    gL
    0.06
    arius
    0.06
    Activations Density 0.001%

    No Known Activations